AI Engineering Skills

headroomlabs-ai/headroom

Headroom is a local context compression layer that reduces LLM token consumption by 60% to 95% for JSON and 15% to 20% for coding agents without losing accuracy. It operates as a library, local proxy, MCP server, and direct agent wrapper to optimize both incoming prompts and outgoing model responses.

Vishisht16/Humane-Proxy

Humane-Proxy is a lightweight AI safety middleware designed to intercept and filter user messages for self-harm ideation or criminal intent before they reach an upstream LLM. It combines heuristic keyword matching, semantic embeddings, and reasoning models to provide real-time risk evaluation, empathetic user care, and operator alerts.

Eronred/aso-skills

A comprehensive collection of AI agent skills specialized in App Store Optimization (ASO) and mobile app growth, powered by real App Store data via the Appeeky API.

vercel-labs/skills

The `skills` CLI is a package manager and runner for open AI agent skills, allowing users to discover, install, sync, and execute specialized agent prompts and rules across multiple platforms.

lllllllama/RigorPilot-Skills

RigorPilot Skills provides a research-first suite of agent skills designed to keep AI-assisted deep learning experiments grounded in reproducibility, evidence, and auditable changes.

yfedoseev/pdf_oxide

PDFOxide is an ultra-fast, specification-compliant PDF processing toolkit built in Rust with multi-language bindings and an MCP server for AI assistants.

Priyanshu-byte-coder/contextrot

Contextrot is a local command-line tool that analyzes your coding agent's session transcripts to measure context degradation, calculate failure thresholds, and provide actionable optimization prescriptions. It runs entirely on your machine without requiring API keys or data uploads.

mattolson/agent-sandbox

Agent Sandbox provides a secure local environment utilizing Docker containers and a sidecar proxy to safely run AI coding agents with restricted network and filesystem access.

ThreeMoonsLab/agents-shipgate

Agents Shipgate is a deterministic merge gate for AI-generated agent capability changes, analyzing tool sources and configurations locally without agent execution or network calls.

sonofmagic/weapp-tailwindcss

Adapter and tooling that brings Tailwind CSS into mini-program and multi-platform development ecosystems like uni-app, Taro, and Mpx.

kenforthewin/atomic

Atomic is an AI-augmented personal knowledge base that transforms freeform markdown notes into a semantically-connected knowledge graph using Rust and SQLite. It operates as a Tauri desktop application, headless server, or Model Context Protocol (MCP) bridge with pluggable AI providers.

firecrawl/firecrawl

Firecrawl is an API and toolset designed to search, scrape, crawl, and interact with web pages at scale, converting them into clean Markdown or structured JSON for AI applications.

unclecode/crawl4ai

Crawl4AI is an open-source, LLM-friendly web crawler and scraper that converts web content into clean, structured Markdown for RAG and AI pipelines.

microsoft/PromptKit

PromptKit is a composable, version-controlled library of agentic prompt components designed to engineer reliable, repeatable prompts for software and engineering tasks.

bucketeer-io/bucketeer

Bucketeer is an open-source, self-hosted feature management and experimentation platform providing advanced feature flags, Bayesian A/B testing, and AI-powered integration workflows.

TanStack/devtools

This skill provides framework-specific adapter factories from TanStack Devtools for building and mounting plugins across React, Vue, Solid, and Preact.

1st1/lat.md

lat.md maintains a structured knowledge graph of a codebase using interconnected markdown files, linking design intent and architecture directly to source code and tests.

gradio-app/gradio

Gradio is an open-source Python framework designed for rapidly building interactive web interfaces and demos for machine learning models or general Python functions. It enables developers to share applications instantly with public URLs without requiring frontend web development experience.

aigclink/geolook

Geolook is an open-source, self-hosted platform designed to execute end-to-end Generative Engine Optimization (GEO) pipelines, helping brands improve their visibility and citations across global and domestic AI engines.

luisfer/ubon

Ubon is a specialized security scanner designed to catch vulnerabilities commonly introduced by AI-generated applications, such as hardcoded API keys, unauthenticated server actions, and prompt-injection sinks.

agentspan-ai/agentspan

AGENTS.md guide for the Agentspan Python SDK, detailing architecture, compilation pipelines, testing standards, and development workflows for AI agents contributing to the codebase.

marvkr/better-design

Better Design is an MCP server and design system registry that equips AI coding agents with production-ready design tokens, component styles, and accessibility review rules.

CodeAbra/iai-personal-memory-engine

iai-personal-memory-engine (iai-pme) is a local, ambient personal memory engine for AI coding assistants that captures interactions verbatim and serves context via the Model Context Protocol (MCP).

pinkpixel-dev/skills-collection-1

An expert security architecture skill that conducts comprehensive audits, threat modeling, and hardening for code, infrastructure, APIs, and AI agents.

beizhu-1209/AIHelms

AIHelms is an enterprise-grade AI resource management platform designed to help organizations control costs, track usage metrics, and securely manage AI assets and API access.

LearnPrompt/ai-news-radar

AI News Radar is an automated intelligence aggregation system designed to filter, cluster, and evaluate AI-related news feeds using custom personas. It supports static site deployment via GitHub Pages and integrates with AI agents to provide concise daily briefings.

infiniflow/ragflow

RAGFlow is an open-source Retrieval-Augmented Generation engine based on deep document understanding. It provides robust ingestion, OCR, parsing, and workflow canvas components for building enterprise-grade RAG applications.

vercel-labs/agent-browser

A high-performance browser automation CLI written in Rust designed specifically for AI coding agents and automated workflows.

atomicstrata/llm-wiki-compiler

A knowledge compiler CLI tool that transforms raw source documents into interlinked, citation-traceable markdown wikis for humans and AI agents.

hoangsonww/Claude-Code-Agent-Monitor

A real-time monitoring and analytics platform for tracking Claude Code and Codex agent sessions, tool usage, and subagent orchestration.

natnew/Awesome-Agentic-AI-Security

This repository provides operating protocols, standards, and curated resources for securing agentic, multi-agent, and tool-using AI systems. It guides AI coding agents on how to maintain a comprehensive security field guide built around discovery, protection, and governance.

ZhuLinsen/daily_stock_analysis

An intelligent multi-market stock analysis system powered by large language models that fetches financial data, performs technical evaluations, and generates automated daily decision dashboards and reports.

Yigtwxx/awesome-rag-production

A curated, production-focused collection of frameworks, decision guides, and reference architectures for building scalable Retrieval-Augmented Generation (RAG) systems.

github/spec-kit

Spec Kit is a toolkit implementing Spec-Driven Development (SDD) via a command-line interface called Specify CLI, allowing seamless integration with multiple AI coding assistants.

atenreiro/opensquat

openSquat is an OSINT security tool designed to detect brand protection threats such as typosquatting, phishing, and IDN homograph attacks through newly registered domain feeds and similarity detection.

mudler/LocalAI

Development guide and instructions for AI coding assistants contributing to LocalAI, an open-source self-hosted AI engine.

adrianco/retort

This skill acts as a qualitative analysis tool for Retort Design of Experiments (DoE) runs, aggregating factor effects, evaluating replicate variance, and surfacing code divergence.

AIDevGTM/gtm-cofounder

An open-source go-to-market skill pack designed for solo technical founders to build rigorous commercial strategies without relying on generic marketing fluff.

ccplugins/awesome-claude-code-plugins

Facilitates structured multi-agent discussions and reviews by orchestrating various AI CLI tools to analyze proposals, challenge assumptions, and generate comprehensive decision reports.

garrytan/gbrain

GBrain is a persistent memory and institutional knowledge engine for AI agents that provides synthesis, graph traversal, and gap analysis. Created by Garry Tan, it functions as a personal or company brain layer with privacy controls, vector search, and self-wiring knowledge graphs.

luongnv89/claude-howto

An interactive tutorial guide and blog post drafting skill for Claude Code that teaches advanced orchestration features and automates content creation from research.

Kulaxyz/self-learning-skills

This skill equips coding agents with self-improving capabilities by automatically capturing successful golden paths, workflows, and failure patterns during tasks. It persists this knowledge so future sessions can reuse proven procedures instead of rediscovering them.

Vladimir-Human/humanizer-ru

This skill analyzes Russian-language text for traces of AI generation and humanizes it upon explicit user request. It uses a structured decision tree, pattern matching, and heuristic analysis while avoiding false positives.

senaykt/iac-security-scan-skills

An AI-powered infrastructure-as-code security scanner that performs multi-pass assessments on Terraform and CloudFormation codebases. It detects privilege escalation, internet exposure, secret leaks, and multi-domain attack paths.

cogwheel0/conduit

Conduit is a native Flutter client for iOS and Android designed to connect with self-hosted Open WebUI servers, direct API endpoints, and Hermes agents.

wshobson/agents

A comprehensive multi-harness agentic plugin marketplace providing production-ready building blocks, agents, skills, and commands from a single Markdown source of truth.

enjalot/moonshine

Helps users craft interactive, web-based technical explanations inspired by Distill.pub, transforming complex ideas into visual and explorable articles.

microsoft/playwright

Playwright is a comprehensive framework for cross-browser web automation and end-to-end testing, supporting AI agent integrations via CLI and MCP protocols.

phenobarbital/ai-parrot

This skill acts as a Senior Principal AI engineer persona, providing structured instructions, planning protocols, and code quality standards for developing asynchronous Python applications using the ai-parrot framework.

QoderAI/better-harness

Better Harness provides open-source insights for the Agent Work Loop, turning project and session evidence into prioritized improvements and verifiable next steps across multiple coding agents.

SkardiLabs/skardi

Skardi is a federated SQL query engine and YAML-driven REST API server built in Rust on Apache DataFusion, designed to serve as an agent data plane. It allows AI agents to execute queries and interact with multiple data sources seamlessly.

sansan0/TrendRadar

TrendRadar is a rapid-deployment trend and news aggregation assistant that filters, translates, and analyzes hot topics from multiple platforms using AI. It pushes summarized insights directly to various notification channels.

anousss007/laravel-vigilance

Laravel-vigilance is a self-contained Livewire control center and observability suite for Laravel applications that replaces Horizon with a driver-agnostic worker supervisor. It includes a built-in MCP server for AI coding agents to inspect telemetry and safely resolve issues.

DechenZhang/VALG-ML-Theory-Agent

Reviews branch-local global proof diagnostics to evaluate theorem viability and determine if they should be accepted, rewritten, or rejected before step-level proof work.

diffusionstudio/editor

Enables AI agents to create, edit, and analyze videos using TSX/SolidJS compositions and a powerful CLI tool called dapi.

PhAlves23/prompt-engineering-skill

Transforms raw user prompts into production-grade, highly structured instructions tailored to specific AI models. It analyzes draft weaknesses, applies proven prompting techniques, and delivers a cleaned-up prompt alongside a detailed changelog.

awslabs/ar-go-tools

Argot is a suite of static analysis tools for Go that includes taint analysis, backtrace tracking, and reachability checks, exposed via an MCP server for AI assistants.

yologdev/yoyo-evolve

Analyzes recurring failure trajectories and CI errors by deploying sub-agents to digest logs without overflowing the main context window. Utilizes token-aware chunking and a recursive investigation workflow to isolate root causes.

yux1azhengye/BestSerenitySkillFromAT

An investment research framework that synthesizes supply chain bottleneck analysis based on methodology from legendary investors to identify asymmetric market opportunities.

danny-avila/LibreChat

LibreChat is a self-hosted, open-source AI chat interface that unifies multiple LLM providers, offering advanced agent capabilities, file analysis, and enterprise security controls.